R Notebook

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.

library(dplyr)
library(ggplot2)
library(tidyr)
library(car)
library(MASS)
library(repr)
library(pals)

getwd()

[1] "C:/Users/Natalie/git_proj/Is-your-electric-car-overpriced-"

ecars_raw = ecars_raw %>% rename(Price = Price.DE., Acceleration = acceleration..0.100.)

Error in `rename()`:
! Can't rename columns that don't exist.
✖ Column `Price.DE.` doesn't exist.
Backtrace:
 1. ecars_raw %>% rename(Price = Price.DE., Acceleration = acceleration..0.100.)
 3. dplyr:::rename.data.frame(., Price = Price.DE., Acceleration = acceleration..0.100.)

make = strsplit(ecars_raw$Car_name, split = ' ')

make_ = c()
n = length(make)

for (i in 1:n) {
  make_[i] = make[[i]][1]
}

ecars_raw$Make = make_

ecars_raw = ecars_raw %>% relocate(Make, .before = Car_name_link)
ecars_raw = ecars_raw %>% relocate(Battery, .after = Car_name_link)
ecars_raw

make_colors = c('#e6194b', '#f58231',  '#ffe119', 
                '#bcf60c','#3cb44b', '#008080',
                '#aaffc3', '#4363d8', '#000075',
                '#46f0f0', '#911eb4', '#e6beff',
                '#f032e6', '#fabebe')

summary(price_model_full)

Call:
lm(formula = Price ~ Battery + Efficiency + Fast_charge + Range + 
    Top_speed + Acceleration, data = ecars)

Residuals:
   Min     1Q Median     3Q    Max 
-53557 -11739   -178   8223  84430 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)  -1.613e+05  2.398e+04  -6.724 8.91e-11 ***
Battery       2.215e+02  3.506e+02   0.632  0.52798    
Efficiency    3.052e+02  1.140e+02   2.678  0.00781 ** 
Fast_charge   1.785e+01  7.819e+00   2.283  0.02315 *  
Range         9.066e+00  6.679e+01   0.136  0.89211    
Top_speed     7.013e+02  7.086e+01   9.897  < 2e-16 ***
Acceleration  1.762e+03  7.746e+02   2.274  0.02366 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 18530 on 300 degrees of freedom
Multiple R-squared:  0.7167,    Adjusted R-squared:  0.711 
F-statistic: 126.5 on 6 and 300 DF,  p-value: < 2.2e-16

forwardAIC = step(price_model_empty, scope, direction = 'forward', k = 2)

Start:  AIC=6415.84
Price ~ 1

               Df  Sum of Sq        RSS    AIC
+ Top_speed     1 2.1023e+11 1.5319e+11 6152.6
+ Battery       1 1.7911e+11 1.8431e+11 6209.4
+ Fast_charge   1 1.3923e+11 2.2419e+11 6269.5
+ Range         1 1.2615e+11 2.3728e+11 6287.0
+ Acceleration  1 1.0296e+11 2.6046e+11 6315.6
+ Efficiency    1 1.1067e+10 3.5235e+11 6408.3
<none>                       3.6342e+11 6415.8

Step:  AIC=6152.62
Price ~ Top_speed

               Df  Sum of Sq        RSS    AIC
+ Efficiency    1 4.2802e+10 1.1039e+11 6054.0
+ Battery       1 1.9965e+10 1.3322e+11 6111.8
+ Acceleration  1 1.5065e+10 1.3812e+11 6122.8
<none>                       1.5319e+11 6152.6
+ Fast_charge   1 2.2387e+08 1.5297e+11 6154.2
+ Range         1 7.0491e+07 1.5312e+11 6154.5

Step:  AIC=6054.03
Price ~ Top_speed + Efficiency

               Df  Sum of Sq        RSS    AIC
+ Fast_charge   1 3519695484 1.0687e+11 6046.1
+ Range         1 3506122724 1.0688e+11 6046.1
+ Battery       1 3063673448 1.0732e+11 6047.4
+ Acceleration  1  915987463 1.0947e+11 6053.5
<none>                       1.1039e+11 6054.0

Step:  AIC=6046.08
Price ~ Top_speed + Efficiency + Fast_charge

               Df  Sum of Sq        RSS    AIC
+ Range         1 2137906570 1.0473e+11 6041.9
+ Battery       1 2032210165 1.0484e+11 6042.2
+ Acceleration  1  713779942 1.0615e+11 6046.0
<none>                       1.0687e+11 6046.1

Step:  AIC=6041.87
Price ~ Top_speed + Efficiency + Fast_charge + Range

               Df  Sum of Sq        RSS    AIC
+ Acceleration  1 1639080066 1.0309e+11 6039.0
<none>                       1.0473e+11 6041.9
+ Battery       1    1076868 1.0473e+11 6043.9

Step:  AIC=6039.03
Price ~ Top_speed + Efficiency + Fast_charge + Range + Acceleration

          Df Sum of Sq        RSS    AIC
<none>                 1.0309e+11 6039.0
+ Battery  1  1.37e+08 1.0295e+11 6040.6

summary(price_model)

Call:
lm(formula = Price_lambda ~ Efficiency + Fast_charge + Range + 
    Top_speed + Acceleration, data = ecars)

Residuals:
       Min         1Q     Median         3Q        Max 
-2.951e-04 -4.127e-05  8.710e-06  4.794e-05  1.467e-04 

Coefficients:
               Estimate Std. Error   t value Pr(>|t|)    
(Intercept)   1.413e+00  5.206e-05 27130.409  < 2e-16 ***
Efficiency    3.059e-06  1.332e-07    22.957  < 2e-16 ***
Fast_charge   1.407e-07  2.675e-08     5.259 2.75e-07 ***
Range         5.510e-07  5.805e-08     9.491  < 2e-16 ***
Top_speed     1.601e-06  2.455e-07     6.524 2.89e-10 ***
Acceleration -4.715e-06  2.603e-06    -1.812    0.071 .  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 6.436e-05 on 301 degrees of freedom
Multiple R-squared:  0.853, Adjusted R-squared:  0.8505 
F-statistic: 349.3 on 5 and 301 DF,  p-value: < 2.2e-16

prediction = predict(price_model, ecars, interval = 'prediction')
confidence = predict(price_model, ecars, interval = 'confidence')
prediction_dollars = ((prediction * lambda) + 1)^(1/lambda)
confidence_dollars = ((confidence * lambda) + 1)^(1/lambda)
predicted_price = data.frame(Name = ecars$Car_name,
                             Make = ecars$Make,
                             Price = ecars$Price/1000,
                             Predicted = (prediction_dollars[,1]/1000),
                             Predict_lwr = (prediction_dollars[,2]/1000),
                             Predict_upr = (prediction_dollars[,3]/1000),
                             Confidence_lwr = (confidence_dollars[,2]/1000),
                             Confidence_upr = (confidence_dollars[,3]/1000))
predicted_price

ggplot(NULL, aes(Predicted_price, Price)) +
      geom_smooth(data = predicted_price, aes(x = Predicted, y = Predicted), col = 'black', linetype = 'dashed') +
      geom_smooth(data = predicted_price, aes(x = Predicted, y = Predict_lwr), col = 'red', linetype = 'dashed') +
      geom_smooth(data = predicted_price, aes(x = Predicted, y = Predict_upr), col = 'red') +
      geom_smooth(data = predicted_price, aes(x = Predicted, y = Confidence_lwr), col = 'blue') +
      geom_smooth(data = predicted_price, aes(x = Predicted, y = Confidence_upr), col = 'blue') +
      geom_ribbon(aes(ymin = predicted_price$Confidence_lwr, ymax = predicted_price$Confidence_upr), fill = "grey70")+
      ylim(25,150) + xlim(25, 140) +
      geom_point(data = predicted_price, aes(x = Predicted, y = Price), alpha = .5) + 
      geom_point(data = most_makes, aes(x = mean_predicted, y = mean_price, col = Make), size = 3) +
      scale_color_manual(values = make_colors) +
      xlab("Predicted Price in 1000s of Euros") + ylab("Price in 1000s of Euros") +
      ggtitle('Price of Electric Vehicles with mean cost per Make')

Error in `geom_ribbon()`:
! Problem while computing aesthetics.
ℹ Error occurred in the 6th layer.
Caused by error:
! object 'Predicted_price' not found
Backtrace:
  1. base (local) `<fn>`(x)
  2. ggplot2:::print.ggplot(x)
  4. ggplot2:::ggplot_build.ggplot(x)
  5. ggplot2:::by_layer(...)
 12. ggplot2 (local) f(l = layers[[i]], d = data[[i]])
 13. l$compute_aesthetics(d, plot)
 14. ggplot2 (local) compute_aesthetics(..., self = self)
 15. base::lapply(aesthetics, eval_tidy, data = data, env = env)
 16. rlang (local) FUN(X[[i]], ...)

testa = ggplot(NULL, aes(Predicted_price, Price)) +
      geom_smooth(data = predicted_price, aes(x = Predicted, y = Predicted), 
                  col = 'blue', size = .8, alpha = .5) +
      geom_smooth(data = predicted_price, aes(x = Predicted, y = Predict_lwr), 
                  col = 'red', linetype = 'dashed', size = .8, alpha = .8) +
      geom_smooth(data = predicted_price, aes(x = Predicted, y = Predict_upr), 
                  col = 'red', linetype = 'dashed',size = .8, alpha = .8) +
      geom_smooth(data = predicted_price, aes(x = Predicted, y = Confidence_lwr), 
                  col = 'black', linetype = 'dashed', size = .8, alpha = .8) +
      geom_smooth(data = predicted_price, aes(x = Predicted, y = Confidence_upr), 
                  col = 'black', linetype = 'dashed', size = .8, alpha = .8) +
      geom_point(data = predicted_price, aes(x = Predicted, y = Price, text = Name), alpha = .5) +
      theme(legend.position = "right", legend.text = element_text(size = 8))+
      ylim(25, 250) + xlim(25, 250) +
      labs(title = "Predicted Price vs. Price for all EV Models",
           caption = "Data source: ToothGrowth",
           x = "Predicted price (euros in thousands)", y = "German Price (euros in thousands)",
           tag = "A")

Warning: Ignoring unknown aesthetics: text

ggplotly(testa, tooltip = c("x", 'y', "text")) 

`geom_smooth()` using method = 'loess' and formula = 'y ~ x'`geom_smooth()` using method = 'loess' and formula = 'y ~ x'Warning: Removed 4 rows containing non-finite values (`stat_smooth()`).`geom_smooth()` using method = 'loess' and formula = 'y ~ x'Warning: Removed 8 rows containing non-finite values (`stat_smooth()`).`geom_smooth()` using method = 'loess' and formula = 'y ~ x'Warning: Removed 1 rows containing non-finite values (`stat_smooth()`).`geom_smooth()` using method = 'loess' and formula = 'y ~ x'Warning: Removed 1 rows containing non-finite values (`stat_smooth()`).

unique(ecars_missing_price$Make)

 [1] "Rolls-Royce" "Hongqi"      "Audi"        "Peugeot"     "Mercedes"    "Opel"        "Polestar"    "Hyundai"    
 [9] "Volkswagen"  "XPENG"       "CUPRA"       "Genesis"     "Maserati"    "Mini"        "Seres"       "Volvo"      
[17] "Ford"        "Lexus"       "Skoda"       "Fiat"        "Kia"         "Toyota"     

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.